© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    a mix of tokens related to specific coding formats, Croatian words relating to SMS messages, and medical terms related to intravitreal treatment

    oai_token-act-pair · gemini-2.0-flash

    ak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amese
    -0.57
    -------------</
    -0.55
    structors
    -0.54
    ghalaya
    -0.52
    RenderAtEndOf
    -0.51
    sividad
    -0.51
    jgl
    -0.51
    nthetic
    -0.50
     promocional
    -0.49
    خدام
    -0.49
    POSITIVE LOGITS
    EDEFAULT
    0.64
    NewUrlParser
    0.54
     defaultstate
    0.52
     inflater
    0.52
    Hentet
    0.50
     InputDecoration
    0.49
    ')(
    0.49
    styleUrls
    0.49
     esternos
    0.48
     unknownFields
    0.47
    Activations Density 0.256%

    No Known Activations